{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T18:23:39Z","timestamp":1778696619203,"version":"3.51.4"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030335083","type":"print"},{"value":"9783030335090","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,10,20]],"date-time":"2019-10-20T00:00:00Z","timestamp":1571529600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-33509-0_69","type":"book-chapter","created":{"date-parts":[[2019,10,19]],"date-time":"2019-10-19T15:39:15Z","timestamp":1571499555000},"page":"736-745","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Learning to Communicate with Multi-agent Reinforcement Learning Using Value-Decomposition Networks"],"prefix":"10.1007","author":[{"given":"Simon","family":"Vanneste","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Astrid","family":"Vanneste","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stig","family":"Bosmans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siegfried","family":"Mercelis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Hellinckx","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,20]]},"reference":[{"key":"69_CR1","unstructured":"Foerster, J., Assael, I.A., de Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137\u20132145 (2016)"},{"key":"69_CR2","unstructured":"Sukhbaatar, S., Fergus, R., et al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, pp. 2244\u20132252 (2016)"},{"key":"69_CR3","unstructured":"Sunehag, P., Lever, G., Gruslys, A., Czarnecki, W.M., Zambaldi, V., Jaderberg, M., Lanctot, M., Sonnerat, N., Leibo, J.Z., Tuyls, K., et\u00a0al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"69_CR4","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press (2018)"},{"key":"69_CR5","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"issue":"6","key":"69_CR6","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1090\/S0002-9904-1954-09848-8","volume":"60","author":"R Bellman","year":"1954","unstructured":"Bellman, R., et al.: The theory of dynamic programming. Bull. Am. Math. Soc. 60(6), 503\u2013515 (1954)","journal-title":"Bull. Am. Math. Soc."},{"issue":"7540","key":"69_CR7","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"69_CR8","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable MDPs. In: 2015 AAAI Fall Symposium Series (2015)"},{"key":"69_CR9","unstructured":"https:\/\/github.com\/minqi\/learning-to-communicate-pytorch"},{"key":"69_CR10","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"69_CR11","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)","DOI":"10.1609\/aaai.v32i1.11492"}],"container-title":["Lecture Notes in Networks and Systems","Advances on P2P, Parallel, Grid, Cloud and Internet Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-33509-0_69","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T02:12:07Z","timestamp":1718071927000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-33509-0_69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,20]]},"ISBN":["9783030335083","9783030335090"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-33509-0_69","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,20]]},"assertion":[{"value":"20 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"3PGCIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on P2P, Parallel, Grid, Cloud and Internet Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Antwerp","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pgcic2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/3pgcic\/2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}